{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nimport zipfile\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.mkdir(\"mydata\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\nwith zipfile.ZipFile(\"../input/dogs-vs-cats/train.zip\", 'r') as zip_ref:\n    zip_ref.extractall(\"./mydata\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def preprocess(img):\n    img = cv2.resize(img,(32,32),cv2.INTER_CUBIC)\n    return img","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport cv2\n%matplotlib inline\n#print(os.listdir(\"mydata/test1\"))\nlabel=[]\ntemp_label=\" \"\ndata=[]\nfor images in list(os.listdir(\"./mydata/train\")):\n    img = cv2.imread(\"./mydata/train/\"+images)\n    img = preprocess(img)\n    #print(img.shape)\n    data.append(img)\n    temp_label = images.split('.')\n    label.append(temp_label[0])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(data))\ndata = np.asarray(data,\"uint8\")\nprint(data.shape)\ndata = data.reshape((data.shape[0],32*32*3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\nlabel = le.fit_transform(label)\nprint(le.classes_)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntrainX,testX,trainY,testY = train_test_split(data,label,test_size=0.33,random_state=42)\nprint(trainX)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier\nmodel = KNeighborsClassifier(n_neighbors=159,n_jobs=-1)\nmodel.fit(trainX,trainY)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import accuracy_score\npredictY = model.predict(testX)\naccuracy_score(testY,predictY)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(accuracy_score)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}